INDEX

Explanations

phrases related to making arguments or stating opinions

oai_token-act-pair · gpt-3.5-turbo

phrases that present arguments or claims

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pione

-0.86

ãĤ¼ãĤ¦ãĤ¹

-0.82

aukee

-0.75

obyl

-0.74

ractor

-0.72

inar

-0.72

apult

-0.72

Listener

-0.71

umat

-0.71

inosaur

-0.71

POSITIVE LOGITS

 although

1.01

 allowing

0.94

 removing

0.92

 despite

0.91

 excessive

0.89

 eliminating

0.88

 adopting

0.87

 restricting

0.85

 insufficient

0.85

 limiting

0.83

Activations Density 0.218%

phrases related to making arguments or stating opinions

phrases that present arguments or claims

No Comments

No Known Activations